Files
AlphaPulse/backend/src/alphapulse/crawler/events.py
T
eezd 89c729092c
Development CI / check-and-build (push) Successful in 2m54s
GitHub Git mirror / mirror (push) Successful in 9s
Development CI / deploy-development (push) Failing after 4m24s
Add resumable US policy news collectors and provenance
Collect official crypto and US policy documents with deterministic screening, full bodies and attachments, bounded retries, and durable history cursors. Preserve publication precision and source identity while keeping new collectors disabled.

Add real Congress, GovInfo, DOJ and Federal Register fixtures, offline capture replay, isolated database validation, and rollout instructions. Validate 982 backend tests, frontend checks, and 57 deployment control tests.
2026-11-04 21:41:04 +08:00

45 lines
1.6 KiB
Python

import json
import uuid
from sqlalchemy import insert
from alphapulse.core.db import SessionLocal
from alphapulse.core.redis import KEY_PREFIX, redis
from alphapulse.models import CrawlLog
LOG_CHANNEL = f"{KEY_PREFIX}pub:logs"
NEWS_CHANNEL = f"{KEY_PREFIX}pub:news"
CONTROL_CHANNEL = f"{KEY_PREFIX}ctl:crawler"
STATUS_KEY = f"{KEY_PREFIX}crawler:status"
# Sources whose list endpoints support historical pagination.
from alphapulse.core.us_news import SOURCES as US_SOURCES
HISTORY_SOURCES = ("wscn_live", "wscn_news", *US_SOURCES)
def start_urls_key(source_code: str) -> str:
return f"{KEY_PREFIX}{source_code}:start_urls"
async def write_logs(rows: list[tuple[str, uuid.UUID | None, str, str]]) -> None:
"""rows: (source_code, run_id, level, message);落库后再发布,前端拿到的日志都带 id"""
if not rows:
return
async with SessionLocal() as session:
result = await session.execute(
insert(CrawlLog).returning(CrawlLog.id, CrawlLog.ts),
[{"source_code": s, "run_id": r, "level": lv, "message": m} for s, r, lv, m in rows],
)
saved = result.all()
await session.commit()
async with redis.pipeline(transaction=False) as pipe:
for (source_code, run_id, level, message), (log_id, ts) in zip(rows, saved, strict=True):
pipe.publish(LOG_CHANNEL, json.dumps({
"id": log_id,
"source_code": source_code,
"run_id": str(run_id) if run_id else None,
"ts": ts.isoformat(),
"level": level,
"message": message,
}, ensure_ascii=False))
await pipe.execute()